python-多线程演练3

标题：

1.Queue线程安全队列:

# encoding=utf-8

from queue import Queue
import time
import threading

# # 队列有四个
#q = Queue(4)
# for x in range(4):
#     q.put(x)
#
# for x in range(4):
#     print(q.get())

# # get  默认阻塞
# q.get(block=True)
# # put 一直阻塞，直到不满
# q.put(block=True)

def set_value(q):
    index = 0
    while True:
        q.put (index)
        index += 1
        time.sleep(3)

def get_value(q):
    while True:
        print(q.get())

def main():
    q = Queue(4)
    # args 需一个列表或参数
    t1 = threading.Thread(target=set_value,args=[q])
    t2 = threading.Thread(target=get_value,args=[q])
    t1.start()
    t2.start()

if __name__ == '__main__':
    main()

演练： 爬取表情包（使用xpath方法）

# xpath
# encoding=utf-8
import requests
from lxml import etree
from urllib import request
# os : 获取文件后缀名
import os
import re
def parse_page(url):
    headers = {
        'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/'
                     '72.0.3626.81 Safari/537.36 SE 2.X MetaSr 1.0'
    }
    response = requests.get(url,headers=headers)
    # text 自动解码正确
    # print(response.text)
    text = response.text
    html = etree.HTML(text)
    imgs = html.xpath('//div[@class="col-sm-9 center-wrap"]//img[@class!="gif"]')
    for img in imgs:
        img_url = img.get('data-original')
        alt = img.get('alt')
        alt = re.sub(r'[\?？\.，。!！]','',alt)
        # extension : 扩展名  进行分割
        suffix = os.path.splitext(img_url)[1]
        filename = alt + suffix
        request.urlretrieve(img_url,'biaoqingbao/'+filename)

def main():
    for x in range(1,18):
        url = 'https://www.doutula.com/photo/list/?page={}'.format(x)
        parse_page(url)
        break

if __name__ == '__main__':
    main()